LLM Guard
Open-source input and output scanners for LLM apps; the repository was archived in July 2026
LLM Guard is an open-source security toolkit for LLM applications, from Protect AI. It wraps model calls with input scanners (prompt injection, toxicity, secrets, code, banned topics) and output scanners (toxicity, bias, sensitive data, relevance, factual consistency).
It sanitizes prompts, detects harmful language and prevents data leakage. It installs via pip. Protect AI was acquired by Palo Alto Networks. MIT licensed.
The GitHub repository was archived in July 2026 and no longer receives updates. The code stays available under its licence; new projects should weigh that against maintained alternatives.
Pricing: Free
Choosing a guardrails tool right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a guardrails tool right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
LLM Guard Alternatives
Explore 64 products in the Observability & Analytics category. View all LLM Guard alternatives.
Guardrails AI
Open-source framework for adding input and output validators around LLM calls
NeMo Guardrails
NVIDIA toolkit for adding programmable guardrails to LLM conversational apps
AiDren
Drop-in security proxy that blocks prompt injection and data leaks in LLM apps by changing one base URL
Dunetrace
Runtime reliability and failure detection for AI agents
TrueFoundry
AI gateway for routing across 250+ LLMs with fallbacks, rate limiting, guardrails, and RBAC
Work on LLM Guard? Feature it at the top of Observability & Analytics.
Is your product missing?